-
mmm_stan
Python/STAN Implementation of Multiplicative Marketing Mix Model, with deep dive into Adstock (carry-over effect), ROAS, and mROAS
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Question: Which Rabbit Hole to fall into? So far, it seems the best solution is either Robyn (most visualizations, lots of support / courses, can be automated on Google Cloud Platform, but uses R and apparently can't forecast), or PyMC (which uses Markov Chain Monte Carlo (MCMC). Additionally, there are some good github projects (MMM_STAN) that use Pystan (that use a domain specific C++ syntax to specify the model and data). Or, should I just use PyMC (in my native python) and then adapt to Robyn once I understand the basics? Does anyone have any thoughts or opinions?
Related posts
-
Marketing background + data science
-
Stan: Statistical modeling and high-performance statistical computation
-
Bayesian Structural Equation Modeling using blavaan
-
Elevate Your Python Skills: Machine Learning Packages That Transformed My Journey as ML Engineer
-
How often do you see Bayesian Statistics or Stan in the DS world? Essential skill or a nice to have?